Hi guys,

i'm a student of University of Genoa (Italy). I'm new on your website and
i have already found some important information for my research. You are
very cool and professional.
Now i write here because i want to try to calculate the Interrupt Latency
for freeRTOS using an ARM LPC23xx.

The idea that i have is that:
i want to generate an interrupt from extern and to misure the time that
will be between when i generate the interrupt and the time when the first
instruction af the interrupt routine will be executed. The misurement
should be made by inserting two probes of an oscilloscope in the interrupt
line and in the output. Then the time that should be between the two pulse
will be the Interrupt Latency. 

THE PROBLEM CORE IS THE CODE!!!

So, i ask you if someone has ever wrote a code to make this or has ever
made a code to calculate Interrupt Latency in some way.

Best Reguards to you all.
Thanks.
Davide.

> The idea that i have is that:
> i want to generate an interrupt from extern and to misure the time that
> will be between when i generate the interrupt and the time when the first
> instruction af the interrupt routine will be executed. The misurement
> should be made by inserting two probes of an oscilloscope in the interrupt
> line and in the output. Then the time that should be between the two pulse
> will be the Interrupt Latency.
>
> THE PROBLEM CORE IS THE CODE!!!
>
> So, i ask you if someone has ever wrote a code to make this or has ever
> made a code to calculate Interrupt Latency in some way.

Yep.  That's a fool proof way to measure interrupt latency.  I've done it 
that way many times.  It's a good exercise to do with any embedded system. 
Sometimes you don't always get the response time you require and if you 
don't measure it, you'll never know for sure.

JJS

John Speth schreef:
>> The idea that i have is that:
>> i want to generate an interrupt from extern and to misure the time that
>> will be between when i generate the interrupt and the time when the first
>> instruction af the interrupt routine will be executed. The misurement
>> should be made by inserting two probes of an oscilloscope in the interrupt
>> line and in the output. Then the time that should be between the two pulse
>> will be the Interrupt Latency.
>>
>> THE PROBLEM CORE IS THE CODE!!!
>>
>> So, i ask you if someone has ever wrote a code to make this or has ever
>> made a code to calculate Interrupt Latency in some way.
> 
> Yep.  That's a fool proof way to measure interrupt latency.  I've done it 
> that way many times.  It's a good exercise to do with any embedded system. 
> Sometimes you don't always get the response time you require and if you 
> don't measure it, you'll never know for sure.

It also helps if you have a scope or logic analyzer at your disposal 
that can trigger if the response time exceeds a certain value. If the 
interrupt latency always stays below that threshold the scope should 
never trigger.

OK! Thanks a lot to all!

I have calculate the researched time with the ROTS IAR PowerPac and it is
very short.

Now the question is: HOW CAN I REGISTER AN APPLICATION ON THE VIC?
Which are the function in FreeRTOS that handle the interrupts?

Thanks.
Bye.
Davide.

HELP! HELP! HELP! 

Have someone an example of using interrupts in FreeRTOS?

Thanks a lot!
Davide.

"lucians" <l...@hotmail.it> wrote in message 
news:8...@giganews.com...
> HELP! HELP! HELP!
>
> Have someone an example of using interrupts in FreeRTOS?

There are plenty in the FreeRTOS.org download - at least two for every port. 
There is also not just one way of doing it.

Write to me directly and I can help you.  r ***dot*** barry [_at_] 
freertos.org.

-- 
Regards,
Richard.

+ http://www.FreeRTOS.org & http://www.FreeRTOS.org/shop
17 official architecture ports, more than 6000 downloads per month.

+ http://www.SafeRTOS.com
Certified by TÜV as meeting the requirements for safety related systems.